Leveraging machine learning to enhance appointment adherence at a novel post-discharge care transition clinic

Seung-Yup Lee; Reid M Eagleson; Larry R Hearld; Madeline J Gibson; Kristine R Hearld; Allyson G Hall; Greer A Burkholder; Jacob McMahon; Shoaib Y Mahmood; Corey T Spraberry; Thalia J Baker; Alison R Garretson; Heather M Bradley; Michael J Mugavero

doi:10.1093/jamiaopen/ooae086

Leveraging machine learning to enhance appointment adherence at a novel post-discharge care transition clinic

JAMIA Open. 2024 Nov 9;7(4):ooae086. doi: 10.1093/jamiaopen/ooae086. eCollection 2024 Dec.

Affiliations

¹ Department of Health Services Administration, The University of Alabama at Birmingham, Birmingham, AL 35233, United States.
² Center for Outcomes and Effectiveness Research and Education, The University of Alabama at Birmingham, Birmingham, AL 35233, United States.
³ Department of Medicine, The University of Alabama at Birmingham, Birmingham, AL 35294, United States.
⁴ College of Science and Mathematics, Auburn University, Auburn, AL 36849, United States.
⁵ UAB Medicine, Birmingham, AL 35233, United States.
⁶ Cooper Green Mercy Health Services Authority, Birmingham, AL 35233, United States.

Abstract

Objective: This study applies predictive analytics to identify patients at risk of missing appointments at a novel post-discharge clinic (PDC) in a large academic health system. Recognizing the critical role of appointment adherence in the success of new clinical ventures, this research aims to inform future targeted interventions to increase appointment adherence.

Materials and methods: We analyzed electronic health records (EHRs) capturing a wide array of demographic, socio-economic, and clinical variables from 2168 patients with scheduled appointments at the PDC from September 2022 to August 2023. Logistic regression, decision trees, and eXtreme Gradient Boosting (XGBoost) algorithms were employed to construct predictive models for appointment adherence.

Results: The XGBoost machine learning model outperformed logistic regression and decision trees with an area under the curve (AUC) of 72% vs 65% and 67%, respectively, in predicting missed appointments, despite limited availability of historical data. Key predictors included patient age, number of days between appointment scheduling and occurrence, insurance status, marital status, and mental health and cardiac disease conditions.

Discussion: Findings underscore the potential of machine learning predictive analytics to significantly enhance patient engagement and operational efficiency in emerging healthcare settings. Optimizing predictive models can help balance the early identification of patients at risk of non-adherence with the efficient allocation of resources.

Conclusion: The study highlights the potential value of employing machine learning techniques to inform interventions aimed at improving appointment adherence in a post-discharge transition clinic environment.

Keywords: appointments and schedules; electronic health records; health services research; healthcare disparities; machine learning; patient compliance; risk factors.